---
title: rag-token-base
canonical_url: "https://www.modelscope.cn/models/facebook/rag-token-base"
md_url: "https://www.modelscope.cn/models/facebook/rag-token-base.md"
repository: facebook/rag-token-base
last_updated: 2025-05-20
license: apache-2.0
model_type:
  - rag
architectures:
  - RagTokenForGeneration
library_name:
  - transformer
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 341
stars: 0
---

# rag-token-base

> rag-token-base - facebook 在 ModelScope 开源的模型。This is a non-finetuned version of the RAG-Token model of the the paper Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks by Patrick Lewis, Ethan Perez, Aleksandara Piktus et al.

facebook/rag-token-base 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可。

- **Repository**: facebook/rag-token-base
- **License**: apache-2.0
- **Downloads**: 341
- **Stars**: 0
- **Last updated**: 2025-05-20

Source: https://www.modelscope.cn/models/facebook/rag-token-base

---

## RAG

This is a non-finetuned version of the RAG-Token model of the the paper [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://arxiv.org/pdf/2005.11401.pdf) 
by Patrick Lewis, Ethan Perez, Aleksandara Piktus et al.

Rag consits of a *question encoder*, *retriever* and a *generator*. The retriever should be a `RagRetriever` instance. The *question encoder* can be any model that can be loaded with `AutoModel` and the *generator* can be any model that can be loaded with `AutoModelForSeq2SeqLM`. 

This model is a non-finetuned RAG-Token model and was created as follows:

```python
from transformers import RagTokenizer, RagRetriever, RagTokenForGeneration, AutoTokenizer

model = RagTokenForGeneration.from_pretrained_question_encoder_generator("facebook/dpr-question_encoder-single-nq-base", "facebook/bart-large")

question_encoder_tokenizer = AutoTokenizer.from_pretrained("facebook/dpr-question_encoder-single-nq-base")
generator_tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large")

tokenizer = RagTokenizer(question_encoder_tokenizer, generator_tokenizer)
model.config.use_dummy_dataset = True
model.config.index_name = "exact"
retriever = RagRetriever(model.config, question_encoder_tokenizer, generator_tokenizer)

model.save_pretrained("./")
tokenizer.save_pretrained("./")
retriever.save_pretrained("./")
```

Note that the model is *uncased* so that all capital input letters are converted to lower-case.

## Usage:

*Note*: the model uses the *dummy* retriever as a default. Better results are obtained by using the full retriever, 
by setting `config.index_name="legacy"` and `config.use_dummy_dataset=False`.
The model can be fine-tuned as follows:

```python
from transformers import RagTokenizer, RagRetriever, RagTokenForGeneration

tokenizer = RagTokenizer.from_pretrained("facebook/rag-token-base")
retriever = RagRetriever.from_pretrained("facebook/rag-token-base")
model = RagTokenForGeneration.from_pretrained("facebook/rag-token-base", retriever=retriever)

input_dict = tokenizer.prepare_seq2seq_batch("who holds the record in 100m freestyle", "michael phelps", return_tensors="pt") 

outputs = model(input_dict["input_ids"], labels=input_dict["labels"])

loss = outputs.loss

# train on loss
```